Automatic Generation of 3-D Curved Object Models by Using the Learning Mechanism of Neural Networks

  • H. B. Zha
  • T. Nagata
  • K. Kumamaru
Part of the Microprocessor-Based and Intelligent Systems Engineering book series (ISCA, volume 9)


The paper addresses the automatic model generation problem that faces us when we attempt to construct a flexible vision system. In the paper, we present an object-modeling method which describes patches composing model object surfaces and uses the described patches as primitive features for the model description. In the model, the patches are recorded in a list structure and their order in the list can be changed according to their different importance in recognizing different objects. A new algorithm for quantifying the importance on the basis of the learning mechanism of neural networks is proposed. It is shown that the model is particularly suitable for interpreting images containing partially occluded objects.


Training Image Model Object Feature Ranking Input Cell Model Patch 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    P. J. Besl, “Geometric Modeling and Computer Vision”, Proc. IEEE, vol.76, pp.936­-958, 1988CrossRefGoogle Scholar
  2. [2]
    R. C. Bolles, and R. A. Cain, “Recognizing and Locating Partially Visible Objects: the Local-Feature-Focus Method”Int. Journal Robotics Res.vol.1, pp.57–82, 1982CrossRefGoogle Scholar
  3. [3]
    R.T. Chin, and C.R. Dyer, “Model-Based Recognition in Robot Vision”Computing Surveysvol.18, pp.67–108, 1986CrossRefGoogle Scholar
  4. [4]
    T.J. Fan, G. Medioni, and R. Nevatia, “Matching 3-D Objects Using Surface Descrip­tions”Proc. Int. Conf. Robotics and Automationpp.1400–1406, 1988Google Scholar
  5. [5]
    T. Nagata, and H. B. Zha, “Recognizing and Locating a Known Object from Multiple Images”, to appear inIEEE Trans. Robotics and Automation Google Scholar
  6. [6]
    Y. H. Pao, Adaptive Pattern Recognition and Neural Networks, Addison-Wesley Pub­lishing Company, Inc., 1989Google Scholar
  7. [7]
    T. Skordas, and R. Horaud“Planning a Strategy for Recognizing Partially Occluded Parts”, in Proc. 8th Int. Joint Conf. Pattern Recognitionpp.1080–1083, 1986Google Scholar
  8. [8]
    J. L. Turney, T. N. Mudge, and R. A. Volz, “Recognizing Partially Occluded Parts”, IEEE Trans. Patt. Analysis Mach. Intell., vol.PAMI-7, pp.410–421, 1985CrossRefGoogle Scholar
  9. [9]
    H.B. Zha, T. Nagata, and K. Kumamaru, “Determination of Feature Points of 3-D Curved Surfaces by Computing Surface Saliency from Range Images”, to appear in Proc. IECON’91, 1991Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1991

Authors and Affiliations

  • H. B. Zha
    • 1
  • T. Nagata
    • 2
  • K. Kumamaru
    • 1
  1. 1.Department of Control Engineering and ScienceKyushu Institute of TechnologyFukuokaJapan
  2. 2.Department of Computer Science and CommunicationEngineering Kyushu UniversityFukuokaJapan

Personalised recommendations